discord
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes message content from Discord, which could contain malicious instructions.
- Ingestion points: Message retrieval and search functions in
scripts/discord_cli.pyingest content from the Discord API. - Boundary markers: The JSON output lacks specific delimiters or instructions to the agent to treat the external data as untrusted.
- Capability inventory: The skill has write capabilities to Discord, including sending messages, adding reactions, creating threads, and pinning messages.
- Sanitization: No sanitization or filtering is performed on the message content retrieved from external sources before it is presented to the agent.
Audit Metadata